Rewritten 2026-08-30: router/mHC/KDA aux kept unquantized. 4bit=QUASAR-init (KL -8.5% vs RTN). ~29-33 tok/s on M3 Ultra. Receipts in each repo.
ALISVOLATPROPRIIS PRO
avlp12
AI & ML interests
MLX quantization, Apple Silicon inference, MoE models, local LLM deployment, medical AI, geopolitical early warning systems, humanoid robotics, semiconductor/memory markets, multi-agent systems
Recent Activity
liked a model about 6 hours ago
openbmb/MiniCPM5-2B liked a model about 7 hours ago
TokenRhythm/NeoHorse-1-4B liked a model 8 days ago
deepseek-ai/DeepSeek-V4.1-FlashOrganizations
None yet
models 41
avlp12/GLM-5.3-Flash-Alis-MLX-4bit
Text Generation • 41B • Updated • 3.32k • 4
avlp12/GLM-5.3-Flash-Alis-MLX-8bit
Text Generation • Updated • 1.63k • 4
avlp12/GLM-5.3-Flash-Alis-MLX-6bit
Text Generation • 60B • Updated • 1.07k
avlp12/GLM-5.3-Flash-Alis-MTP-Drafter
7B • Updated • 910 • 1
avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw
Text Generation • 751B • Updated • 571 • 2
avlp12/Motif-3-Beta-Alis-MLX-Dynamic-4.5bpw
Text Generation • Updated • 265 • 1
avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw
Text Generation • Updated • 308 • 3
avlp12/Motif-3-Beta-Alis-MLX-8bit
Text Generation • Updated • 107 • 2
avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw
Text Generation • Updated • 1.45k • 2
avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw-VLM
Image-Text-to-Text • 1T • Updated • 855 • 2
datasets 0
None public yet